export_evaluation_set · Scifinder Route MCP: Risk & Policy

WHAT IT DOES

What export_evaluation_set does on Scifinder Route

AI agents use export_evaluation_set to create or update resources in Scifinder Route — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scifinder Route environment.

WHY IT NEEDS A POLICY

Why export_evaluation_set needs a policy

The tool generates and exports data (reaction steps as JSONL), which is reversible (the exported file can be deleted or regenerated). It does not irreversibly delete data (Destructive), does not move money (Financial), does not execute arbitrary code (Execute), and does retrieve/query data but the primary action is creating an output file. Write is the most appropriate category.

From the tool's definition Tool name 'export_evaluation_set' and description 'Export extracted reaction steps as JSONL for manual labeling' indicates the tool creates or outputs data in a structured format (JSONL files). This is a write/create operation that produces new data artifacts.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

export_evaluation_set Rate-limited

export_evaluation_set stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "export_evaluation_set": {
      "limits": [
        {
          "counter": "export_evaluation_set_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Scifinder Route, so you can run agents against it safely.

FAQ

Questions about export_evaluation_set

What does the export_evaluation_set tool do? +

Export extracted reaction steps as JSONL for manual labeling and regression checks. It is categorised as a Write tool in the Scifinder Route MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on export_evaluation_set? +

Register the Scifinder Route MCP server in PolicyLayer and add a rule for export_evaluation_set: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Scifinder Route. Nothing to install.

What risk level is export_evaluation_set? +

export_evaluation_set is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit export_evaluation_set? +

Yes. Add a rate_limit block to the export_evaluation_set rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block export_evaluation_set completely? +

Set action: deny in the PolicyLayer policy for export_evaluation_set. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides export_evaluation_set? +

export_evaluation_set is provided by the Scifinder Route MCP server (kettly1260/scifinder-route-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.